Back to News

Google DeepMind releases AlphaGenome Atlas, map of 9B human DNA variants

#deepmind#genomics#ai#dataset

Google DeepMind has released AlphaGenome Atlas, a 1PB dataset cataloging predicted molecular effects for approximately 9 billion possible single-letter DNA changes in the human genome. The company describes it as the most comprehensive catalogue of how genetic mutations affect molecular biology.

Coverage timeline

  1. Google DeepMind Blog
    AlphaGenome Atlas: A predictive map of every possible DNA letter change in the human genome

    AlphaGenome Atlas maps the molecular effects of 9 billion single-letter DNA variants across the human genome.

  2. Techmeme
    Google DeepMind releases AlphaGenome Atlas, a 1PB dataset of predicted molecular effects for all ~9B possible single-letter DNA changes in the human genome (Google)

    Google : Google DeepMind releases AlphaGenome Atlas, a 1PB dataset of predicted molecular effects for all ~9B possible single-letter DNA changes in the human genome — AlphaGenome Atlas is the most comprehensive catalogue of how genetic mutations affect molecular biology. — VP Science, Google DeepMind & Chief Scientist, Google Cloud

Related stories

  • Google DeepMind unveils SynthID Bio to watermark AI-designed proteins

    Google DeepMind introduced SynthID Bio, a proof-of-concept family of watermarking methods for AI-generated proteins, aimed at supporting biosecurity and scientific integrity. The methods are designed to mark AI-designed proteins while preserving their biological function.

    2 reports · 2 sources

  • Google DeepMind: Gemma open models pass 1B downloads, 100K+ variants

    Google DeepMind announced that its Gemma family of open models has surpassed 1 billion downloads, with developers publishing over 100,000 Gemma model variants over the past two years. The announcement highlights the broad adoption and community impact of these open models.

    1 reports · 1 sources

  • Google moves DeepMind AI responsibility team to global affairs unit

    According to an internal email reported by the Wall Street Journal, Google is moving DeepMind's approximately 90-person AI responsibility team, which focuses on risks and societal impact of AI, to Google's global affairs unit. Researchers have raised concerns about the effect on their independence and ability to detect threats from the newest models.

    2 reports · 1 sources

  • DeepSeek releases Harness agent framework as MIT-licensed developer preview

    DeepSeek has released DeepSeek Harness, an open-source AI agent framework with a plugin-based architecture where every capability is a plugin, under the MIT license as a developer preview. The framework, which runs locally and resembles Claude Code, has gained nearly 95,000 GitHub stars within a day of release, with over 700 community repositories adding plugins for features like long-term memory, games, and visual models. Its underlying Cordis kernel enables reversible side effects and dynamic plugin loading, including a 'create mode' that lets the agent modify its own plugin tree at runtime.

    5 reports · 4 sources731 points · 308 comments

News updates every hour. Subscribe in your RSS reader to get new stories automatically.

Subscribe